Journal ArticleDOI
A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Reads0
Chats0
TLDR
A universal statistical model for texture images in the context of an overcomplete complex wavelet transform is presented, demonstrating the necessity of subgroups of the parameter set by showing examples of texture synthesis that fail when those parameters are removed from the set.Abstract:
We present a universal statistical model for texture images in the context of an overcomplete complex wavelet transform. The model is parameterized by a set of statistics computed on pairs of coefficients corresponding to basis functions at adjacent spatial locations, orientations, and scales. We develop an efficient algorithm for synthesizing random images subject to these constraints, by iteratively projecting onto the set of images satisfying each constraint, and we use this to test the perceptual validity of the model. In particular, we demonstrate the necessity of subgroups of the parameter set by showing examples of texture synthesis that fail when those parameters are removed from the set. We also demonstrate the power of our model by successfully synthesizing examples drawn from a diverse collection of artificial and natural textures.read more
Citations
More filters
Posted Content
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TL;DR: This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.
Proceedings ArticleDOI
Image Style Transfer Using Convolutional Neural Networks
TL;DR: A Neural Algorithm of Artistic Style is introduced that can separate and recombine the image content and style of natural images and provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation.
Proceedings ArticleDOI
Multiscale structural similarity for image quality assessment
TL;DR: This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions, and develops an image synthesis method to calibrate the parameters that define the relative importance of different scales.
Book
Computer Vision: Algorithms and Applications
TL;DR: Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images and takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene.
Proceedings ArticleDOI
A Bayesian hierarchical model for learning natural scene categories
Li Fei-Fei,Pietro Perona +1 more
TL;DR: This work proposes a novel approach to learn and recognize natural scene categories by representing the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning.
References
More filters
Journal ArticleDOI
Statistics of natural images: Scaling in the woods.
TL;DR: In this article, the statistics of an ensemble of images taken in the woods were studied and it was shown that local quantities such as contrast and power spectra exhibit scaling with a nontrivial exponent.
Proceedings Article
Statistics of Natural Images: Scaling in the Woods
Daniel Ruderman,William Bialek +1 more
TL;DR: This work gathers images from the woods and finds that these scenes possess an ensemble scale invariance, and this non-Gaussian character cannot be removed through local linear filtering, meaning information is maximized at fixed channel variance.
Journal ArticleDOI
Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling
TL;DR: The resulting model, called FRAME (Filters, Random fields And Maximum Entropy), is a Markov random field (MRF) model, but with a much enriched vocabulary and hence much stronger descriptive ability than the previous MRF models used for texture modeling.
Journal ArticleDOI
A multiscale random field model for Bayesian image segmentation
Charles A. Bouman,M. Shapiro +1 more
TL;DR: Simulations on synthetic images indicate that the new algorithm performs better and requires much less computation than MAP estimation using simulated annealing, and is found to improve classification accuracy when applied to the segmentation of multispectral remotely sensed images with ground truth data.